计算机科学 ›› 2012, Vol. 39 ›› Issue (6): 270-273.
• 图形图像 • 上一篇 下一篇
赵英男,文学志,成亚萍
出版日期:
发布日期:
Online:
Published:
摘要: 近年来,融合可见光和近红外光的人脸图像特征识别成为一个研究热点。对该领域中的快速人脸识别技术 进行研究,并给出了一个具体的实现方案。该方案主要包括以下3种技术:原始样本的下采样;基于稀疏表征原理,选 取测试样本的叮近部来代替原始训练样本;加权决策融合。在CSIS T人脸库上的实验结果表明,和同类算法相比,所 提算法在识别率和计算速度上均有提高。
关键词: 稀疏表征,可见光图像,近红外光图像,数据融合,人脸识别
Abstract: Recently,the face recognition of the fusion of visible (VIS) and near infrared (NIR) images has attracted more attention. Here we studied the fast face recognition in this field and gave an applied scheme in detail, which in- eludes three main techniques;down-sampling of the original samples,sparse representation based selection of M-neigh- hors to substitute the original training samples and the weighted decision fusion strategy. Comparing with the classic al- gorithms, the experiments on CSIST face databases show that our scheme can achieve higher classification accuracy with a lower computation load.
Key words: Sparse representation, Visual image, Ncar infrared image, Data fusion, Face recognition
赵英男,文学志,成亚萍. 基于稀疏表征的可见光和近红外光人脸图像融合快速识别算法[J]. 计算机科学, 2012, 39(6): 270-273. https://doi.org/
0 / / 推荐
导出引用管理器 EndNote|Reference Manager|ProCite|BibTeX|RefWorks
链接本文: https://www.jsjkx.com/CN/
https://www.jsjkx.com/CN/Y2012/V39/I6/270
Cited